| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.8369690011481055, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03673938002296211, | |
| "grad_norm": 0.9278978109359741, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.6167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03673938002296211, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5629, | |
| "eval_samples_per_second": 31.991, | |
| "eval_steps_per_second": 8.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07347876004592423, | |
| "grad_norm": 0.9947828650474548, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.5255, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11021814006888633, | |
| "grad_norm": 1.719213604927063, | |
| "learning_rate": 0.0001, | |
| "loss": 3.392, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14695752009184845, | |
| "grad_norm": 1.7546511888504028, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 3.5766, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18369690011481057, | |
| "grad_norm": 1.9130165576934814, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 2.7926, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22043628013777267, | |
| "grad_norm": 3.421264410018921, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.9667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2571756601607348, | |
| "grad_norm": 2.740537643432617, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 2.596, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2939150401836969, | |
| "grad_norm": 2.477086305618286, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 2.3228, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.330654420206659, | |
| "grad_norm": 1.5250732898712158, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1207, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36739380022962115, | |
| "grad_norm": 1.927494764328003, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 2.6965, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4041331802525832, | |
| "grad_norm": 1.0458897352218628, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 2.1316, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.44087256027554533, | |
| "grad_norm": 1.563544750213623, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.9629, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 1.739471197128296, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 1.9402, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5143513203214696, | |
| "grad_norm": 0.9345394372940063, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 2.2439, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5510907003444316, | |
| "grad_norm": 0.8077870011329651, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0604, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5878300803673938, | |
| "grad_norm": 1.165358304977417, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 1.8347, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6245694603903559, | |
| "grad_norm": 1.2270612716674805, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 2.3273, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.661308840413318, | |
| "grad_norm": 1.1496846675872803, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.9949, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6980482204362801, | |
| "grad_norm": 1.7061587572097778, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 1.4995, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7347876004592423, | |
| "grad_norm": 1.7375099658966064, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 1.4207, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7715269804822044, | |
| "grad_norm": 0.8804224729537964, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.0821, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8082663605051664, | |
| "grad_norm": 0.94223952293396, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 1.8211, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8450057405281286, | |
| "grad_norm": 1.558922290802002, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 1.9614, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8817451205510907, | |
| "grad_norm": 1.367186188697815, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0158, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9184845005740528, | |
| "grad_norm": 1.1374205350875854, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 1.5267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9184845005740528, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5676, | |
| "eval_samples_per_second": 31.897, | |
| "eval_steps_per_second": 8.293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 1.1894108057022095, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 1.3724, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9919632606199771, | |
| "grad_norm": 1.7453018426895142, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2575, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0287026406429391, | |
| "grad_norm": 2.426978349685669, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 3.0889, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0654420206659012, | |
| "grad_norm": 1.067915916442871, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 1.7397, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1021814006888633, | |
| "grad_norm": 1.5281691551208496, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7003, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1389207807118256, | |
| "grad_norm": 1.1140716075897217, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 1.7107, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1756601607347876, | |
| "grad_norm": 0.9925709366798401, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 1.2638, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2123995407577497, | |
| "grad_norm": 1.4794470071792603, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2194, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2491389207807118, | |
| "grad_norm": 0.6699503660202026, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.531, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2858783008036738, | |
| "grad_norm": 1.4114007949829102, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 2.5394, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.322617680826636, | |
| "grad_norm": 1.0232292413711548, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6208, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3593570608495982, | |
| "grad_norm": 1.3607043027877808, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 1.1508, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3960964408725602, | |
| "grad_norm": 1.3985986709594727, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 1.4222, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 1.3112035989761353, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1613, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4695752009184844, | |
| "grad_norm": 1.5417652130126953, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.938, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5063145809414467, | |
| "grad_norm": 1.0807812213897705, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 1.291, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5430539609644087, | |
| "grad_norm": 0.9991649985313416, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.8465, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5797933409873708, | |
| "grad_norm": 1.1210612058639526, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 1.1593, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.616532721010333, | |
| "grad_norm": 1.4225951433181763, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 1.2247, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.653272101033295, | |
| "grad_norm": 1.6108145713806152, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.4636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6900114810562572, | |
| "grad_norm": 1.3490177392959595, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.9067, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7267508610792193, | |
| "grad_norm": 1.700265884399414, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.9955, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7634902411021813, | |
| "grad_norm": 1.0068745613098145, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0694, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8002296211251436, | |
| "grad_norm": 1.1462795734405518, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 1.4829, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8369690011481055, | |
| "grad_norm": 1.6393139362335205, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 1.2071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8369690011481055, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.5666, | |
| "eval_samples_per_second": 31.917, | |
| "eval_steps_per_second": 8.298, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |